Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15271
    Prev
    Next
    INDEX
    Explanations

    temporal references and conjunctions that indicate chronological events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.92
     Theſe
    -0.85
    تقاوى
    -0.81
     Cæsar
    -0.78
     Jefus
    -0.78
     auroit
    -0.78
     purpoſe
    -0.77
     reaſon
    -0.76
     vectorielles
    -0.75
    ſelf
    -0.74
    POSITIVE LOGITS
     then
    0.90
     kemudian
    0.81
    then
    0.78
     thereafter
    0.73
     Danach
    0.72
     subsequently
    0.71
     later
    0.68
     ثم
    0.68
     luego
    0.67
     बाद
    0.67
    Activations Density 0.215%

    No Known Activations